swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7221
- Accuracy: 0.7737
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.1848 | 0.94 | 11 | 1.7186 | 0.4158 |
1.4956 | 1.96 | 23 | 1.2667 | 0.5632 |
1.0692 | 2.98 | 35 | 0.9042 | 0.7 |
0.75 | 4.0 | 47 | 0.8151 | 0.7316 |
0.598 | 4.94 | 58 | 0.7305 | 0.7737 |
0.4762 | 5.62 | 66 | 0.7221 | 0.7737 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 25